D
Darjn Esposito
Researcher at Information Technology University
Publications - 20
Citations - 455
Darjn Esposito is an academic researcher from Information Technology University. The author has contributed to research in topics: Adder & Least mean squares filter. The author has an hindex of 8, co-authored 20 publications receiving 256 citations. Previous affiliations of Darjn Esposito include University of Naples Federico II.
Papers
More filters
Journal ArticleDOI
Approximate Multipliers Based on New Approximate Compressors
TL;DR: Novel approximate compressors and an algorithm to exploit them for the design of efficient approximate multiplier circuits are proposed and synthesized approximate multipliers for several operand lengths using a 40-nm library.
Journal ArticleDOI
Variable Latency Speculative Parallel Prefix Adders for Unsigned and Signed Operands
TL;DR: Five novel VLA architectures, based on Brent-Kung, Ladner-Fisher, Sklansky, Hybrid Han-Carlson, and Carry increment parallel-prefix topologies are proposed and results show that proposed VLAs outperform previous speculative architectures and standard (non-speculative) adders when high-speed is required.
Proceedings ArticleDOI
Low-power approximate MAC unit
TL;DR: A MAC unit, specialized to perform 2D convolution, is designed following the proposed approach and implemented in TSMC 40nm technology in four different configurations, with power savings more than 60%, compared to standard, exact MAC.
Journal ArticleDOI
Variable Latency Speculative Han-Carlson Adder
TL;DR: Results show that proposed variable latency Han-Carlson adder outperforms both previously proposed speculative Kogge-Stone architectures and non-speculative adders, when high-speed is required and it is shown that non- Speculation adders remain the best choice when the speed constraint is relaxed.
Proceedings ArticleDOI
On the use of approximate adders in carry-save multiplier-accumulators
TL;DR: This paper investigates the use of approximate adders in the final stage of a carry save multiplier-accumulator (MAC), designed for image filtering application, and proposes a design flow based on synthesis tools, starting from HDL description.